Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

A minimal Jekyll Theme to host your resume (CV)

Interface for Controllable Expressive Talking Machine

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

🔆 📝 A reading list focused on Multimodal Emotion Recognition (MER) 👂👄 👀 💬

Understanding emotions with Neural Networks (Python, Scikit-Learn, Keras) and the Ravdess dataset.

⏩ Generating speech in a single forward pass without any attention!